pythonwise /

#!/usr/bin/env python

from urllib import urlopen
import re
import webbrowser

W3_URL = ""
FILE_NAME = "/tmp/html-entities.html"
find_entity = re.compile("!ENTITY\s+([A-Za-z][A-Za-z0-9]+)").search

fo = open(FILE_NAME, "wt")

print >> fo, "<html><body><table border=\"1\">"

for line in urlopen(W3_URL):
    match = find_entity(line)
    if match:
        entity = match.groups()[0]
        print >> fo, "<tr><td>%s</td><td>&%s;</td></tr>" % (entity, entity)
print >> fo, "</table></body></html>"
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.